Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2390 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1993407 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1918648 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1989813 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1913603 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1438378 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0615. Min Act: -0.0001

Data Index: 770968 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1878335 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0626. Min Act: -0.0001

Data Index: 379105 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1281419 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0617. Min Act: -0.0001

Data Index: 570028 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1245482 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1245242 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1844434 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0720. Min Act: -0.0001

Data Index: 982286 (The Pile)

Max Activating Token Index: 75

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0644. Min Act: -0.0001

Data Index: 914284 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0675. Min Act: -0.0001

Data Index: 876774 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0746. Min Act: -0.0001

Data Index: 537080 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0640. Min Act: -0.0001

Data Index: 302908 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1983853 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1417286 (The Pile)

Max Activating Token Index: 110